Segmentation method, device and electronic equipment for lower extremity artery image, and storage medium

Abstract

The application discloses a lower limb artery image segmentation method and device, electronic equipment and storage medium. The lower limb artery image segmentation method comprises the following steps: acquiring a plurality of cross-sectional images corresponding to a lower limb artery image, determining a segmentation mask image corresponding to each cross-sectional image; determining a bony marker corresponding to the lower limb artery image; determining a boundary point of the lower limb artery image based on the segmentation mask image information and the bony marker, determining a target segmentation corresponding to the lower limb artery image according to the boundary point; and determining a target segmentation image corresponding to the target segmentation based on the lower limb artery image. The accuracy of the lower limb artery image segmentation is ensured, and the accuracy of the determined target segmentation image is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer application, and in particular to a segmentation method and device for lower limb artery images, an electronic device and a storage medium. BACKGROUND

[0002] At present, lower limb computed tomography angiography and magnetic resonance angiography are widely used for qualitative and positioning diagnosis and preoperative evaluation of lower limb arterial diseases. After post-processing by computer software, three-dimensional reconstruction, maximum density projection and multi-planar reconstruction of lower limb arteries can be displayed, providing important imaging basis for diagnosis and treatment of lower limb arterial diseases. The segmentation of femoral popliteal artery includes common femoral artery, deep femoral artery, superficial femoral artery, popliteal artery P1, P2 and P3 segments. The clinical significance of preoperative image evaluation is that different endovascular or open surgical treatment techniques should be used for lesions located in different segments or continuously across multiple segments. If the vascular lesions can be located in advance, it will help surgeons to make accurate preoperative preparation and planning.

[0003] However, the existing image post-processing technology cannot realize accurate automatic segmentation of femoral popliteal artery, which is not conducive to accurate preoperative evaluation. The main reasons are: 1) there is no marked branch vessel from the superficial femoral artery to the end of the popliteal artery, so the traditional segmentation method based on vascular bifurcation point cannot be used; 2) the anatomical boundary point of the superficial femoral artery and the popliteal artery is the adductor tendon hiatus, but this anatomical boundary point is a soft tissue structure, which is difficult to accurately describe on CTA images and other images. Therefore, the accuracy of segmenting lower limb artery images is poor. SUMMARY

[0004] The present application provides a segmentation method and device for lower limb artery images, an electronic device and a storage medium to solve the technical problem of poor accuracy of segmenting lower limb artery images.

[0005] According to an aspect of the present application, a segmentation method for lower limb artery images is provided, wherein the method comprises:

[0006] Obtaining a plurality of cross-sectional images corresponding to the lower limb artery images, determining a segmentation mask image corresponding to each cross-sectional image, wherein the segmentation mask image includes at least one of a femoral popliteal artery mask, a femur mask, a patella mask and a tibia mask;

[0007] Determining a bony marker corresponding to the lower limb artery images, wherein the bony marker includes at least one of femoral cortex, superior patellar margin and tibial platform superior margin;

[0008] determine a boundary point of the lower limb artery image based on the segmentation mask image and the bony marker, and determine a target segment corresponding to the lower limb artery image according to the boundary point, wherein the target segment includes at least one of a superficial femoral artery segment, a popliteal artery P1 segment, a popliteal artery P2 segment, and a popliteal artery P3 segment.

[0009] determine a target segmentation image corresponding to the target segment based on the lower limb artery image.

[0010] According to another aspect of the present application, there is provided a device for segmenting a lower limb artery image, wherein the device comprises:

[0011] an image processing module configured to obtain a plurality of cross-sectional images corresponding to the lower limb artery image, and determine a segmentation mask image corresponding to each of the cross-sectional images, wherein the segmentation mask image includes at least one of a femoropopliteal artery mask, a femur mask, a patella mask, and a tibia mask;

[0012] a marker determination module configured to determine a bony marker corresponding to the lower limb artery image, wherein the bony marker includes at least one of a femoral cortex, a superior patella margin, and a superior tibia platform margin;

[0013] a segment determination module configured to determine a boundary point of the lower limb artery image based on the segmentation mask image and the bony marker, and determine a target segment corresponding to the lower limb artery image according to the boundary point, wherein the target segment includes at least one of a superficial femoral artery segment, a popliteal artery P1 segment, a popliteal artery P2 segment, and a popliteal artery P3 segment;

[0014] a segment processing module configured to determine a target segmentation image corresponding to the target segment based on the lower limb artery image.

[0015] According to another aspect of the present application, there is provided an electronic device, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein

[0018] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for segmenting a lower limb artery image according to any one of the embodiments of the present application.

[0019] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the method for segmenting a lower limb artery image according to any one of the embodiments of the present application when executed by the processor.

[0020] The technical scheme of the embodiment of the present application, by acquiring a plurality of cross-sectional images corresponding to the lower extremity artery image, determining a segmentation mask image corresponding to each of the cross-sectional images, wherein the segmentation mask image includes at least one of the femoral popliteal artery mask, the femur mask, the patella mask, and the tibia mask, so that the cross-sectional image corresponding to the lower extremity artery image can be subjected to voxel analysis; determining a bony marker corresponding to the lower extremity artery image, wherein the bony marker includes at least one of the femoral cortex, the superior edge of the patella, and the superior edge of the tibial platform, thereby improving the accuracy of the determined bony marker corresponding to the lower extremity artery image; determining a demarcation point of the lower extremity artery image based on the segmentation mask image and the bony marker, and determining a target segment corresponding to the lower extremity artery image according to the demarcation point, wherein the target segment includes at least one of the superficial femoral artery segment, the popliteal artery P1 segment, the popliteal artery P2 segment, and the popliteal artery P3 segment, thereby improving the accuracy of the determined demarcation point of the lower extremity artery image, and further improving the accuracy of the determined target segment corresponding to the lower extremity artery image; determining a target segmentation image corresponding to the target segment based on the lower extremity artery image, thereby ensuring the accuracy of segmentation of the lower extremity artery image, and improving the accuracy of the determined target segmentation image.

[0021] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0023] Figure 1 is a flow chart of a lower extremity artery image segmentation method provided by the first embodiment of the present application;

[0024] Figure 2 is a scene diagram of the lower extremity artery image for implementing the embodiment of the present application.

[0025] Figure 3 is a scene diagram of the popliteal artery mask and the femur mask for implementing the embodiment of the present application.

[0026] Figure 4 is a scene diagram of the patella mask for implementing the embodiment of the present application.

[0027] Figure 5This is a scene diagram of the tibial mask implemented in an embodiment of the present invention.

[0028] Figure 6 This is a flowchart of a method for segmenting lower extremity arterial images according to Embodiment 2 of the present invention;

[0029] Figure 7 This is a schematic diagram of the structure of a segmentation device for lower limb arterial imaging according to Embodiment 3 of the present invention;

[0030] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the segmentation method for lower limb arterial images according to an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1 This is a flowchart illustrating a method for segmenting lower limb arterial images according to Embodiment 1 of the present invention. This embodiment is applicable to image processing scenarios. The method can be executed by a lower limb arterial image segmentation device, which can be implemented in hardware and / or software and can be configured in a computer. Figure 1 As shown, the method includes:

[0035] S110. Acquire multiple cross-sectional images corresponding to the lower limb artery images, and determine the segmentation mask image corresponding to each cross-sectional image.

[0036] The lower extremity arterial images mentioned above can be understood as images of the lower extremity arteries (see reference). Figure 2 ).

[0037] Figure 2 This includes the adductor tendon 201, femur 202, patella 203, tibia 204, anterior tibial artery 205, superficial femoral artery segment 206, popliteal artery P1 segment 207, popliteal artery P2 segment 208, and popliteal artery P3 segment 209.

[0038] The cross-sectional image can be understood as the image corresponding to the cross-section of the lower limb artery image. The segmentation mask image can be understood as the image of the segmentation mask corresponding to the cross-sectional image (see reference). Figures 3 to 5 ).

[0039] Optionally, the segmentation mask image includes at least one of the following: the popliteal artery mask, the femoral mask, the patellar mask, and the tibial mask; wherein, the popliteal artery mask can be understood as the mask corresponding to the popliteal artery (see reference). Figures 3 to 5 The femoral mask can be understood as the mask corresponding to the femur (see reference). Figure 3 The patellar mask mentioned above can be understood as a mask corresponding to the patella (see reference). Figure 4 The tibial mask can be understood as a mask corresponding to the tibia (see reference). Figure 5 ).

[0040] in, Figure 3 Including the femoral mask 301 and the femoral popliteal artery mask 302. Figure 4 This includes the patellar mask 401, the femoral mask 402, and the femoropopliteal artery mask 403. Figure 5 This includes the tibial mask 501 and the femoropopliteal artery mask 502.

[0041] Specifically, interpolation and matrix cropping operations can be performed on multiple cross-sectional images corresponding to lower limb artery images to obtain the target cross-sectional image, thereby removing background irrelevant to the target region from the cross-sectional image to the greatest extent possible. Further, the target cross-sectional image can be segmented into pixels or voxels using segmentation algorithms and manual segmentation to obtain a segmentation mask image. Optionally, the segmentation algorithm may include region growing algorithms, thresholding algorithms, or deep learning semantic algorithms, etc.

[0042] Optionally, determining the segmentation mask image corresponding to each of the cross-sectional images includes:

[0043] For each of the cross-sectional images, an affine coordinate system is obtained, and the affine coordinate system is fused with the cross-sectional image;

[0044] The fused cross-sectional image is segmented into voxels to obtain the segmentation mask image corresponding to the cross-sectional image;

[0045] The affine coordinate system includes an X-axis, a Y-axis, and a Z-axis. The X-axis is parallel to the cross-section of the lower limb artery image, the Z-axis is perpendicular to the cross-section, and the Y-axis is parallel to the cross-section and perpendicular to both the X-axis and the Z-axis. Specifically, each cross-sectional image can be traversed based on preset traversal coordinates and preset directions corresponding to the affine coordinate system. The preset traversal coordinates can be understood as preset starting coordinates for traversing the cross-sectional images. It is understood that the determination of the preset traversal coordinates is related to the selection of the affine coordinate system. Therefore, in this embodiment, the preset traversal coordinates can be preset according to scenario requirements and are not specifically limited here. Optionally, the preset traversal coordinates can be the Z-axis coordinates corresponding to the starting point of the superficial femoral artery. For example, the preset traversal coordinates can be Z-axis coordinates with a coordinate value of 510.

[0046] The preset direction can be understood as a preset direction for traversing the cross-sectional image. In this embodiment of the invention, the preset direction can be preset according to scene requirements, and is not specifically limited here. For example, the preset direction can be the Z-axis direction of the affine coordinate system. For example, the Z-axis direction of the affine coordinate system can be a top-down direction perpendicular to the cross-section.

[0047] S120. Determine the bony landmarks corresponding to the lower limb arterial images.

[0048] The bony landmarks can be understood as bones with a marking function. Optionally, the bony landmarks may include at least one of the femoral cortex, the superior border of the patella, and the superior border of the tibial plateau.

[0049] S130. Determine the boundary point of the lower limb artery image based on the segmentation mask image and the bony markers, and determine the target segment corresponding to the lower limb artery image according to the boundary point.

[0050] The dividing point can be understood as the point that determines the target segment corresponding to the lower limb arterial image. The target segment can be understood as the segmentation result of the target corresponding to the lower limb arterial image. Optionally, the target segment includes at least one of the superficial femoral artery segment, popliteal artery P1 segment, popliteal artery P2 segment, and popliteal artery P3 segment (see reference). Figure 2 ).

[0051] It is important to understand that the boundary between the superficial femoral artery and the popliteal artery is the adductor hiatus. The superficial femoral artery becomes the popliteal artery after passing through the adductor tendon. The lower edge of the adductor hiatus is often close to the femoral cortex. Therefore, in actual interventional radiology procedures, the junction of the artery and the femoral cortex can be regarded as the boundary between the superficial femoral artery segment and the popliteal artery P1 segment when the patient is in the prone position. In interventional radiology, the junction of the upper edge of the patella and the projection of the popliteal artery is the boundary between the P1 and P2 segments, where the popliteal artery runs basically vertically. In interventional radiology, the tibial plateau is the boundary between the P2 and P3 segments of the popliteal artery. The tibial plateau is characterized by being the widest point on both sides in the coronal plane, and its width gradually increases above the tibial plateau and gradually decreases below it.

[0052] In summary, specifically, based on the boundary point determined by the femoral cortex, the superficial femoral artery segment corresponding to the lower limb arterial image can be determined; based on the boundary point determined by the superior border of the patella, the popliteal artery P1 segment corresponding to the lower limb arterial image can be determined; based on the boundary point determined by the superior border of the tibial plateau, the popliteal artery P2 and P3 segments corresponding to the lower limb arterial image can be determined (see reference). Figure 2 ).

[0053] S140. Determine the target segmentation image corresponding to the target segment based on the lower limb artery image.

[0054] The target segmented image can be understood as the segmented image obtained by segmenting the lower limb artery image.

[0055] The technical solution of this invention involves acquiring multiple cross-sectional images corresponding to lower limb arterial images, determining a segmentation mask image corresponding to each cross-sectional image, wherein the segmentation mask image includes at least one of the femoral-popliteal artery mask, femoral mask, patellar mask, and tibial mask, so that the cross-sectional images corresponding to the lower limb arterial images can be subjected to voxel analysis; and determining bony markers corresponding to the lower limb arterial images, wherein the bony markers include at least one of the femoral cortex, the superior border of the patella, and the upper border of the tibial plateau, thereby improving... The accuracy of the bony landmarks corresponding to the determined lower limb arterial images was improved; the boundary points of the lower limb arterial images were determined based on the segmentation mask image and the bony landmarks, and the target segments corresponding to the lower limb arterial images were determined according to the boundary points. The target segments include at least one of the superficial femoral artery segment, the popliteal artery P1 segment, the popliteal artery P2 segment, and the popliteal artery P3 segment, thus improving the accuracy of the determined boundary points of the lower limb arterial images and further improving the precision of the determined target segments corresponding to the lower limb arterial images; a target segmented image corresponding to the target segments was determined based on the lower limb arterial images, ensuring the precision of the segmentation of the lower limb arterial images and improving the accuracy of the determined target segmented images.

[0056] Example 2

[0057] Figure 6 This is a flowchart of a method for segmenting lower limb arterial images according to Embodiment 2 of the present invention. This embodiment addresses the method described in the previous embodiment, which determines the boundary points of the lower limb arterial image based on the segmentation mask image and the bony markers, and refines the target segments corresponding to the lower limb arterial image based on these boundary points. Figure 6 As shown, the method includes:

[0058] S210. Acquire multiple cross-sectional images corresponding to the lower limb artery images, and determine the segmentation mask image corresponding to each cross-sectional image.

[0059] S220. Determine the bony markers corresponding to the lower limb arterial images.

[0060] S230. Determine the first boundary image where the femoral cortex is located, obtain the Z-axis coordinate value corresponding to the first boundary image, obtain the first coordinate value, and use the first coordinate value as the first boundary point of the lower limb arterial image.

[0061] Optionally, the target segment includes the superficial femoral artery segment, the segmentation mask image includes the femoral popliteal artery mask and the femoral mask, and the bony markers include the femoral cortex.

[0062] The first boundary image can be understood as a cross-sectional image of the femoral cortex. In this embodiment of the invention, the cross-sectional image of the femoral cortex can be used as the first boundary image. The first coordinate value can be understood as the Z-axis coordinate value corresponding to the first boundary image. The first boundary point can be understood as the boundary point corresponding to the first coordinate value.

[0063] Optionally, determining the first boundary image where the femoral cortex is located includes:

[0064] For each of the cross-sectional images, a first difference is determined based on the X-axis coordinate values ​​of the voxels in the femoral popliteal artery mask and the femoral mask;

[0065] Determine the product of the first difference corresponding to the current cross-sectional image and the first difference corresponding to the previous cross-sectional image adjacent to the current cross-sectional image;

[0066] If the product is less than or equal to zero for the first time, the current cross-sectional image is determined as the first boundary image where the femoral cortex is located.

[0067] The first difference can be understood as the difference determined based on the X-axis coordinate values ​​of the voxels in the femoral popliteal artery mask and the femoral mask.

[0068] Optionally, determining the first difference based on the X-axis coordinate values ​​of voxels in the femoral popliteal artery mask and the femoral mask includes:

[0069] The maximum value among the X-axis coordinates of each voxel of the femoral mask is determined to obtain the first maximum value, and the minimum value among the X-axis coordinates of each voxel of the femoral popliteal artery mask is determined to obtain the first minimum value.

[0070] The first difference is obtained by subtracting the first maximum value from the first minimum value.

[0071] Wherein, the first maximum value can be understood as the maximum X-axis coordinate value among all voxels of the femoral-popliteal artery mask. The first minimum value can be understood as the minimum X-axis coordinate value among all voxels of the femoral mask. The first difference can be understood as the difference between the first maximum value and the first minimum value.

[0072] It is important to understand that in all cross-sectional images prior to the first dividing point, depending on whether the image is left or right, the first maximum value of the femoral cortex is always less than (or always greater than) the first minimum value of the femoropopliteal artery mask; that is, the sign of the first difference remains unchanged until the first dividing point, at which point a sign abrupt change occurs. Specifically, exemplarily, the formula for determining the first dividing image where the femoral cortex is located can be as follows:

[0073] D = (X1 - X2) 本层 * (X1-X2) 上一层

[0074] Where X1 represents the first maximum value, X2 represents the first minimum value, and (X1-X2) 本层 This represents the first difference (X1-X2) corresponding to the current cross-sectional image. 上一层 The first difference is represented by the previous cross-sectional image, and D represents the product.

[0075] Furthermore, when D≤0 occurs for the first time, the current cross-sectional image is determined as the first boundary image where the femoral cortex is located.

[0076] S240. Based on the first dividing point, the lower limb artery image is segmented to obtain the superficial femoral artery segment corresponding to the femoropopliteal artery mask.

[0077] Optionally, the target segment includes the popliteal artery P1 segment, the segmentation mask image includes the patellar mask, and the bony landmark includes the superior border of the patella;

[0078] The step of determining the boundary points of the lower limb arterial image based on the segmentation mask image and the bony markers, and determining the target segment corresponding to the lower limb arterial image based on the boundary points, includes:

[0079] The cross-sectional image in which the patellar mask first appears is determined as the second boundary image where the upper edge of the patella is located;

[0080] Obtain the Z-axis coordinate value corresponding to the second boundary image to obtain the second coordinate value, and use the second coordinate value as the second boundary point of the lower limb arterial image;

[0081] Based on the second dividing point, the lower limb artery image is segmented to obtain the popliteal artery P1 segment corresponding to the femoropopliteal artery mask.

[0082] The second boundary image can be understood as a cross-sectional image of the superior edge of the patella. In this embodiment of the invention, the cross-sectional image of the superior edge of the patella can be used as the second boundary image. The second coordinate value can be understood as the Z-axis coordinate value corresponding to the second boundary image. The second boundary point can be understood as the boundary point corresponding to the second coordinate value.

[0083] Optionally, the target segment includes the popliteal artery P2 segment and / or the popliteal artery P3 segment, the segmentation mask image includes a tibial mask, and the bony landmark includes the upper edge of the tibial plateau;

[0084] The step of determining the boundary points of the lower limb arterial image based on the segmentation mask image and the bony markers, and determining the target segment corresponding to the lower limb arterial image based on the boundary points, includes:

[0085] Determine the third boundary image where the upper edge of the tibial plateau is located, obtain the Z-axis coordinate value corresponding to the third boundary image, obtain the third coordinate value, and use the third coordinate value as the third boundary point of the lower extremity arterial image;

[0086] Based on the third dividing point, the lower limb artery image is segmented to obtain the popliteal artery P2 segment corresponding to the femoropopliteal artery mask and the popliteal artery P3 segment corresponding to the femoropopliteal artery mask.

[0087] The third boundary image can be understood as the cross-sectional image of the upper edge of the tibial plateau. In this embodiment of the invention, the cross-sectional image of the upper edge of the tibial plateau can be used as the third boundary image. The third coordinate value can be understood as the Z-axis coordinate value corresponding to the third boundary image. The third boundary point can be understood as the boundary point corresponding to the third coordinate value.

[0088] Optionally, determining the third boundary image where the upper edge of the tibial plateau is located includes:

[0089] For each of the cross-sectional images, the maximum value among the X-axis coordinates of each voxel of the tibial mask is determined to obtain the second maximum value, and the minimum value among the X-axis coordinates of each voxel of the tibial mask is determined to obtain the second minimum value.

[0090] The difference between the second maximum value and the second minimum value is used to obtain the second difference value corresponding to each cross-sectional image;

[0091] The cross-sectional image corresponding to the largest second difference is determined, and the current cross-sectional image is determined as the third boundary image where the upper edge of the tibial plateau is located.

[0092] The second maximum value can be understood as the maximum X-axis coordinate value among all voxels of the tibial mask. The second minimum value can be understood as the minimum X-axis coordinate value among all voxels of the tibial mask. The second difference can be understood as the difference between the second maximum value and the second minimum value.

[0093] Specifically, and exemplarily, the formula for calculating the third boundary image where the upper edge of the tibial plateau is located can be as follows:

[0094] F = |X3 - X4|

[0095] Where X3 represents the second minimum value, X4 represents the second maximum value, and F represents the second difference value.

[0096] Furthermore, the cross-sectional image corresponding to the largest F is determined, and the cross-sectional image corresponding to the largest F is determined as the third boundary image where the upper edge of the tibial plateau is located.

[0097] Optionally, determining the target segmentation image corresponding to the target segment based on the lower limb arterial image includes:

[0098] A mask image corresponding to the target segment is determined, and the mask image is superimposed on the lower limb artery image to obtain the target segmentation image.

[0099] The mask image can be understood as the mask corresponding to the femoropopliteal artery in the lower limb arterial image and the target segment. Specifically, the femoropopliteal artery mask corresponding to the superficial femoral artery segment can be updated to the superficial femoral artery mask; the femoropopliteal artery mask corresponding to the popliteal artery P1 segment can be updated to the popliteal artery P1 segment mask; the femoropopliteal artery mask corresponding to the popliteal artery P2 segment can be updated to the popliteal artery P2 segment mask; the femoropopliteal artery mask corresponding to the popliteal artery P3 segment can be updated to the popliteal artery P3 segment mask; and the acquired superficial femoral artery mask, popliteal artery P1 segment mask, popliteal artery P2 segment mask, and popliteal artery P3 segment mask are superimposed on the lower limb arterial image to obtain the target segmentation image.

[0100] S250. Determine the target segmentation image corresponding to the target segment based on the lower limb artery image.

[0101] The technical solution of this invention involves determining the first boundary image where the femoral cortex is located, obtaining the Z-axis coordinate value corresponding to the first boundary image, and using the first coordinate value as the first boundary point of the lower limb arterial image. Based on the first boundary point, the lower limb arterial image is segmented to obtain the superficial femoral artery segment corresponding to the femoropopliteal artery mask. This improves the accuracy of determining the superficial femoral artery segment corresponding to the femoropopliteal artery mask.

[0102] Optional, specific, and overall procedures for segmentation methods in lower extremity arterial imaging can be:

[0103] Step 1: Acquire multiple cross-sectional images (DICOM format) corresponding to the lower extremity arterial images, with dimensions of 512×512×1024. Perform voxel interpolation on these images using the Bspline method to obtain an updated array (1024×1024×2048). Obtain voxels in the first dimension (255-767), the second dimension (255-767), and the third dimension (1-2048), and update them into a new array with dimensions of 512×512×2048. Merge the array with an affine coordinate system (XYZ) to obtain a NiFTI format file.

[0104] Step 2: Obtain the affine coordinate system information of multiple cross-sectional images corresponding to the lower extremity arterial images.

[0105] Step 3: Create the tag file: Perform voxel segmentation based on the file processed in Step 2. The segmentation method is threshold segmentation, and manual segmentation is performed to add and remove corresponding voxels to obtain the segmentation file (NiFTI format). The tag names are as follows:

[0106] Mask 1: femoral-popliteal artery; Mask 2: femur; Mask 3: patella; Mask 4: tibia.

[0107] Step 4: In this file, Z=510 represents the starting point of the superficial femoral artery, and Z=1560 represents the terminal point of the popliteal artery. Execute the loop algorithm statement, starting from Z=510, traverse each voxel array, obtain and store the X1 and X2 values ​​for each layer, and calculate D=(X1-X2). 本层 * (X1-X2) 上一层 Continue until D=0 or D<0, then record the Z value of that layer as 1100.

[0108] Step 5: Execute the loop algorithm statement starting from Z=1101, traverse each layer of the voxel array until the patellar mask voxel appears for the first time in a certain layer, and record the Z value of that layer as 1250.

[0109] Step 6: Execute the loop algorithm statement starting from Z=1250, traverse each voxel array, obtain and store the tibial mask parameters X3 and X4, calculate F=|X3-X4| and store it. After the traversal is complete, the layer with the maximum value of F is obtained at Z=1400.

[0110] Step 7: Redefine the mask layer and save it as a new NiFTI format segmentation file.

[0111] In layer Z=510-1100, mask 1 is redefined as mask 5 (superficial femoral artery).

[0112] In layers Z=1101-1250, mask 1 is redefined as mask 6 (popliteal artery P1 segment).

[0113] In layers Z=1251-1400, mask 1 is redefined as mask 7 (popliteal artery P2 segment);

[0114] In layers Z=1401-1560, mask 1 is redefined as mask 8 (popliteal artery P3 segment).

[0115] Step 8: Merge the affine coordinate system information obtained in Step 2 with the segmented file obtained in Step 7 to obtain a NiFTI file format with spatial measurement units.

[0116] Step 9: Overlay the semantic segmentation image from Step 8 onto the lower limb CTA baseline image to obtain the final automated segmentation result.

[0117] This invention enables rapid and accurate automatic segmentation of the femoral-popliteal artery on lower limb arterial imaging, determining the boundaries between the superficial femoral artery segment, the popliteal artery P1 segment, the popliteal artery P2 segment, and the popliteal artery P3 segment. The treatment strategies for lesions in the superficial femoral artery and the popliteal artery differ significantly. This lower limb arterial imaging segmentation method allows for preoperative assessment of lesion involvement, enabling adjustments to treatment strategies and improving the efficiency and precision of open surgery and interventional treatment of the lower limb arteries.

[0118] Example 3

[0119] Figure 7 This is a schematic diagram of a segmentation device for lower limb arterial imaging provided in Embodiment 3 of the present invention. Figure 7 As shown, the device includes: an image processing module 310, a marker determination module 320, a segmentation determination module 330, and a segmentation processing module 340.

[0120] The image processing module 310 is used to acquire multiple cross-sectional images corresponding to the lower limb artery images and determine a segmentation mask image corresponding to each cross-sectional image, wherein the segmentation mask image includes at least one of the femoral-popliteal artery mask, femoral mask, patellar mask, and tibial mask; the marker determination module 320 is used to determine the bony markers corresponding to the lower limb artery images, wherein the bony markers include at least one of the femoral cortex, the superior border of the patella, and the upper border of the tibial plateau; the segmentation determination module 330 is used to determine the boundary points of the lower limb artery images based on the segmentation mask images and the bony markers, and determine the target segments corresponding to the lower limb artery images according to the boundary points, wherein the target segments include at least one of the superficial femoral artery segment, popliteal artery P1 segment, popliteal artery P2 segment, and popliteal artery P3 segment; and the segmentation processing module 340 is used to determine the target segmentation image corresponding to the target segment based on the lower limb artery images.

[0121] The technical solution of this invention involves acquiring multiple cross-sectional images corresponding to lower limb arterial images, determining a segmentation mask image corresponding to each cross-sectional image, wherein the segmentation mask image includes at least one of the femoral-popliteal artery mask, femoral mask, patellar mask, and tibial mask, so that the cross-sectional images corresponding to the lower limb arterial images can be subjected to voxel analysis; and determining bony markers corresponding to the lower limb arterial images, wherein the bony markers include at least one of the femoral cortex, the superior border of the patella, and the upper border of the tibial plateau, thereby improving... The accuracy of the bony landmarks corresponding to the determined lower limb arterial images was improved; the boundary points of the lower limb arterial images were determined based on the segmentation mask image and the bony landmarks, and the target segments corresponding to the lower limb arterial images were determined according to the boundary points. The target segments include at least one of the superficial femoral artery segment, the popliteal artery P1 segment, the popliteal artery P2 segment, and the popliteal artery P3 segment, thus improving the accuracy of the determined boundary points of the lower limb arterial images and further improving the precision of the determined target segments corresponding to the lower limb arterial images; a target segmented image corresponding to the target segments was determined based on the lower limb arterial images, ensuring the precision of the segmentation of the lower limb arterial images and improving the accuracy of the determined target segmented images.

[0122] Optionally, the image processing module 310 is used for:

[0123] For each of the cross-sectional images, an affine coordinate system is obtained, and the affine coordinate system is fused with the cross-sectional image;

[0124] The fused cross-sectional image is segmented into voxels to obtain the segmentation mask image corresponding to the cross-sectional image;

[0125] The affine coordinate system includes an X-axis, a Y-axis, and a Z-axis. The X-axis is parallel to the cross-section of the lower limb artery image, the Z-axis is perpendicular to the cross-section, and the Y-axis is parallel to the cross-section and perpendicular to both the X-axis and the Z-axis.

[0126] Optionally, the target segment includes the superficial femoral artery segment, the segmentation mask image includes the femoral popliteal artery mask and the femoral mask, and the bony markers include the femoral cortex;

[0127] The segmentation determination module 330 includes: a first boundary point determination submodule and an image segmentation submodule.

[0128] The first boundary point determination submodule is used to determine the first boundary image where the femoral cortex is located, obtain the Z-axis coordinate value corresponding to the first boundary image, obtain the first coordinate value, and use the first coordinate value as the first boundary point of the lower limb arterial image.

[0129] The image segmentation submodule is used to segment the lower limb artery image based on the first dividing point to obtain the superficial femoral artery segment corresponding to the femoropopliteal artery mask.

[0130] Optionally, the first boundary point determination submodule includes: a first difference determination unit, a product determination unit, and a first boundary image determination unit.

[0131] The first difference determination unit is used to determine a first difference for each of the cross-sectional images based on the X-axis coordinate values ​​of the voxels in the femoral popliteal artery mask and the femoral mask.

[0132] The product determination unit is used to determine the product of the first difference corresponding to the current cross-sectional image and the first difference corresponding to the previous cross-sectional image adjacent to the current cross-sectional image;

[0133] The first boundary image determination unit is used to determine the current cross-sectional image as the first boundary image where the femoral cortex is located when the product first appears to be less than or equal to zero.

[0134] Optionally, the first difference determination unit is used for:

[0135] The maximum value among the X-axis coordinates of each voxel of the femoral mask is determined to obtain the first maximum value, and the minimum value among the X-axis coordinates of each voxel of the femoral popliteal artery mask is determined to obtain the first minimum value.

[0136] The first difference is obtained by subtracting the first maximum value from the first minimum value.

[0137] Optionally, the target segment includes the popliteal artery P1 segment, the segmentation mask image includes the patellar mask, and the bony landmark includes the superior border of the patella;

[0138] The segmentation determination module 330 is used for:

[0139] The cross-sectional image in which the patellar mask first appears is determined as the second boundary image where the upper edge of the patella is located;

[0140] Obtain the Z-axis coordinate value corresponding to the second boundary image to obtain the second coordinate value, and use the second coordinate value as the second boundary point of the lower limb arterial image;

[0141] Based on the second dividing point, the lower limb artery image is segmented to obtain the popliteal artery P1 segment corresponding to the femoropopliteal artery mask.

[0142] Optionally, the target segment includes the popliteal artery P2 segment and / or the popliteal artery P3 segment, the segmentation mask image includes a tibial mask, and the bony landmark includes the upper edge of the tibial plateau;

[0143] The segmentation determination module 330 includes: a third boundary point determination submodule and an image processing submodule.

[0144] The third boundary point determination submodule is used to determine the third boundary image where the upper edge of the tibial plateau is located, obtain the Z-axis coordinate value corresponding to the third boundary image, obtain the third coordinate value, and use the third coordinate value as the third boundary point of the lower extremity arterial image.

[0145] The image processing submodule is used to segment the lower limb artery image according to the third dividing point to obtain the popliteal artery P2 segment and the popliteal artery P3 segment corresponding to the femoropopliteal artery mask.

[0146] Optionally, the third boundary point determination submodule is used for:

[0147] For each of the cross-sectional images, the maximum value among the X-axis coordinates of each voxel of the tibial mask is determined to obtain the second maximum value, and the minimum value among the X-axis coordinates of each voxel of the tibial mask is determined to obtain the second minimum value.

[0148] The difference between the second maximum value and the second minimum value is used to obtain the second difference value corresponding to each cross-sectional image;

[0149] The cross-sectional image corresponding to the largest second difference is determined, and the current cross-sectional image is determined as the third boundary image where the upper edge of the tibial plateau is located.

[0150] Optionally, the segmentation processing module 340 is used for:

[0151] A mask image corresponding to the target segment is determined, and the mask image is superimposed on the lower limb artery image to obtain the target segmentation image.

[0152] The lower extremity arterial imaging segmentation device provided in this embodiment of the invention can execute the lower extremity arterial imaging segmentation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0153] Example 4

[0154] Figure 8 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0155] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0156] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0157] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the segmentation method for lower extremity arterial images.

[0158] In some embodiments, the method for segmenting lower extremity arterial images can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for segmenting lower extremity arterial images described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method for segmenting lower extremity arterial images by any other suitable means (e.g., by means of firmware).

[0159] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0160] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0161] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0162] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0163] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0164] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0165] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0166] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for segmenting lower extremity arterial images, characterized in that, include: Multiple cross-sectional images corresponding to lower limb arterial images are acquired, and a segmentation mask image corresponding to each cross-sectional image is determined. The segmentation mask image includes at least one of the femoral popliteal artery mask, femoral mask, patellar mask, and tibial mask. Identify the bony landmarks corresponding to the lower extremity arterial images, wherein the bony landmarks include at least one of the femoral cortex, the superior border of the patella, and the superior border of the tibial plateau; The boundary points of the lower limb arterial image are determined based on the segmentation mask image and the bony markers. The target segments corresponding to the lower limb arterial images are determined based on the boundary points. The target segments include at least one of the superficial femoral artery segment, popliteal artery P1 segment, popliteal artery P2 segment, and popliteal artery P3 segment. Based on the lower limb arterial images, a target segmentation image corresponding to the target segment is determined; Determining the segmentation mask image corresponding to each of the cross-sectional images includes: For each of the cross-sectional images, an affine coordinate system is obtained, and the affine coordinate system is fused with the cross-sectional image; The fused cross-sectional image is segmented into voxels to obtain the segmentation mask image corresponding to the cross-sectional image; The affine coordinate system includes an X-axis, a Y-axis, and a Z-axis. The X-axis is parallel to the cross-section of the lower limb artery image, the Z-axis is perpendicular to the cross-section, and the Y-axis is parallel to the cross-section and perpendicular to both the X-axis and the Z-axis. The target segment includes the superficial femoral artery segment, the segmentation mask image includes the femoral popliteal artery mask and the femoral mask, and the bony markers include the femoral cortex; The step of determining the boundary points of the lower limb arterial image based on the segmentation mask image and the bony markers, and determining the target segment corresponding to the lower limb arterial image based on the boundary points, includes: Determine the first boundary image where the femoral cortex is located, obtain the Z-axis coordinate value corresponding to the first boundary image, obtain the first coordinate value, and use the first coordinate value as the first boundary point of the lower limb arterial image; Based on the first dividing point, the lower limb artery image is segmented to obtain the superficial femoral artery segment corresponding to the femoropopliteal artery mask; The determination of the first boundary image where the femoral cortex is located includes: For each of the cross-sectional images, a first difference is determined based on the X-axis coordinate values ​​of the voxels in the femoral popliteal artery mask and the femoral mask; Determine the product of the first difference corresponding to the current cross-sectional image and the first difference corresponding to the previous cross-sectional image adjacent to the current cross-sectional image; If the product is less than or equal to zero for the first time, the current cross-sectional image is determined as the first boundary image where the femoral cortex is located.

2. The method according to claim 1, characterized in that, Determining the first difference based on the X-axis coordinate values ​​of voxels in the femoral popliteal artery mask and the femoral mask includes: The maximum value among the X-axis coordinates of each voxel of the femoral mask is determined to obtain the first maximum value, and the minimum value among the X-axis coordinates of each voxel of the femoral popliteal artery mask is determined to obtain the first minimum value. The first difference is obtained by subtracting the first maximum value from the first minimum value.

3. The method according to claim 1, characterized in that, The target segment includes the popliteal artery P1 segment, the segmentation mask image includes the patellar mask, and the bony landmark includes the superior border of the patella; The step of determining the boundary points of the lower limb arterial image based on the segmentation mask image and the bony markers, and determining the target segment corresponding to the lower limb arterial image based on the boundary points, includes: The cross-sectional image in which the patellar mask first appears is determined as the second boundary image where the upper edge of the patella is located; Obtain the Z-axis coordinate value corresponding to the second boundary image to obtain the second coordinate value, and use the second coordinate value as the second boundary point of the lower limb arterial image; Based on the second dividing point, the lower limb artery image is segmented to obtain the popliteal artery P1 segment corresponding to the femoropopliteal artery mask.

4. The method according to claim 3, characterized in that, The target segment includes popliteal artery P2 segment and / or popliteal artery P3 segment, the segmentation mask image includes tibial mask, and the bony landmark includes the upper edge of the tibial plateau; The step of determining the boundary points of the lower limb arterial image based on the segmentation mask image and the bony markers, and determining the target segment corresponding to the lower limb arterial image based on the boundary points, includes: Determine the third boundary image where the upper edge of the tibial plateau is located, obtain the Z-axis coordinate value corresponding to the third boundary image, obtain the third coordinate value, and use the third coordinate value as the third boundary point of the lower extremity arterial image; Based on the third dividing point, the lower limb artery image is segmented to obtain the popliteal artery P2 segment corresponding to the femoropopliteal artery mask and the popliteal artery P3 segment corresponding to the femoropopliteal artery mask.

5. The method according to claim 4, characterized in that, The determination of the third boundary image where the upper edge of the tibial plateau is located includes: For each of the cross-sectional images, the maximum value among the X-axis coordinates of each voxel of the tibial mask is determined to obtain the second maximum value, and the minimum value among the X-axis coordinates of each voxel of the tibial mask is determined to obtain the second minimum value. The difference between the second maximum value and the second minimum value is used to obtain the second difference value corresponding to each cross-sectional image; The cross-sectional image corresponding to the largest second difference is determined, and the current cross-sectional image is determined as the third boundary image where the upper edge of the tibial plateau is located.

6. The method according to claim 5, characterized in that, The step of determining the target segmentation image corresponding to the target segment based on the lower limb arterial image includes: A mask image corresponding to the target segment is determined, and the mask image is superimposed on the lower limb artery image to obtain the target segmentation image.

7. A segmentation device for lower extremity arterial imaging, characterized in that, include: The image processing module is used to acquire multiple cross-sectional images corresponding to lower limb arterial images and determine a segmentation mask image corresponding to each cross-sectional image, wherein the segmentation mask image includes at least one of the femoral popliteal artery mask, femoral mask, patellar mask and tibial mask; A marker determination module is used to determine the bony markers corresponding to the lower extremity arterial images, wherein the bony markers include at least one of the femoral cortex, the superior border of the patella, and the superior border of the tibial plateau; The segmentation determination module is used to determine the boundary point of the lower limb artery image based on the segmentation mask image and the bony markers, and to determine the target segment corresponding to the lower limb artery image according to the boundary point, wherein the target segment includes at least one of the superficial femoral artery segment, popliteal artery P1 segment, popliteal artery P2 segment and popliteal artery P3 segment; The segmentation processing module is used to determine the target segmentation image corresponding to the target segment based on the lower limb arterial image; The image processing module is used for: For each of the cross-sectional images, an affine coordinate system is obtained, and the affine coordinate system is fused with the cross-sectional image; The fused cross-sectional image is segmented into voxels to obtain the segmentation mask image corresponding to the cross-sectional image; The affine coordinate system includes an X-axis, a Y-axis, and a Z-axis. The X-axis is parallel to the cross-section of the lower limb artery image, the Z-axis is perpendicular to the cross-section, and the Y-axis is parallel to the cross-section and perpendicular to both the X-axis and the Z-axis. The target segment includes the superficial femoral artery segment, the segmentation mask image includes the femoral popliteal artery mask and the femoral mask, and the bony markers include the femoral cortex; The segmentation determination module includes: a first boundary point determination submodule and an image segmentation submodule; The first boundary point determination submodule is used to determine the first boundary image where the femoral cortex is located, obtain the Z-axis coordinate value corresponding to the first boundary image, obtain the first coordinate value, and use the first coordinate value as the first boundary point of the lower limb arterial image. The image segmentation submodule is used to segment the lower limb artery image according to the first dividing point to obtain the superficial femoral artery segment corresponding to the femoropopliteal artery mask; The first boundary point determination submodule includes: a first difference determination unit, a product determination unit, and a first boundary image determination unit; The first difference determination unit is used to determine a first difference for each of the cross-sectional images based on the X-axis coordinate values ​​of the voxels in the femoral popliteal artery mask and the femoral mask. The product determination unit is used to determine the product of the first difference corresponding to the current cross-sectional image and the first difference corresponding to the previous cross-sectional image adjacent to the current cross-sectional image; The first boundary image determination unit is used to determine the current cross-sectional image as the first boundary image where the femoral cortex is located when the product first appears to be less than or equal to zero.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the segmentation method for lower extremity arterial images according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the segmentation method for lower extremity arterial images according to any one of claims 1-6.

Images